{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T07:40:59Z","timestamp":1776498059643,"version":"3.51.2"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JP23K24926"],"award-info":[{"award-number":["JP23K24926"]}]},{"name":"New Energy and Industrial Technology Development Organization"},{"name":"INVERSE","award":["101136067"],"award-info":[{"award-number":["101136067"]}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3402089","type":"journal-article","created":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T17:31:51Z","timestamp":1715880711000},"page":"69690-69699","source":"Crossref","is-referenced-by-count":4,"title":["Bidirectional Progressive Neural Networks With Episodic Return Progress for Emergent Task Sequencing and Robotic Skill Transfer"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1901-8473","authenticated-orcid":false,"given":"Suzan Ece","family":"Ada","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8842-5536","authenticated-orcid":false,"given":"Hanne","family":"Say","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Özyeğin University, İstanbul, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9597-2731","authenticated-orcid":false,"given":"Emre","family":"Ugur","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Boğaziçi University, İstanbul, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3051-6038","authenticated-orcid":false,"given":"Erhan","family":"Oztop","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Özyeğin University, İstanbul, Turkey"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-41610-1_203-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0921-8890(95)00004-Y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO58561.2023.10355028"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.22009"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41539-021-00110-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2023.1199682"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2012.03.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2008.02209.x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref11","first-page":"1331","article-title":"CURIOUS: Intrinsically motivated modular multi-goal reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Colas"},{"key":"ref12","first-page":"1859","article-title":"Curiosity-driven development of tool use precursors: A computational model","volume-title":"Proc. 38th Annu. Conf. Cognit. Sci. Soc. (COGSCI)","author":"Forestier"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.02.006"},{"key":"ref14","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"Achiam","year":"2017","journal-title":"arXiv:1703.01732"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091363"},{"key":"ref16","first-page":"15146","article-title":"Knowledge transfer in multi-task deep reinforcement learning for continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xu"},{"key":"ref17","article-title":"Distral: Robust multitask reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Teh"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206049"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10733"},{"key":"ref20","article-title":"Decoding multitask DQN in the world of minecraft","volume-title":"Proc. 13th Eur. Workshop Reinforcement Learn. (EWRL), 11th Women Mach. Learn. Workshop Deep Reinforcement Learn. Workshop","author":"Liu"},{"key":"ref21","article-title":"From machine learning to robotics: Challenges and opportunities for embodied intelligence","author":"Roy","year":"2021","journal-title":"arXiv:2110.15245"},{"key":"ref22","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref23","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume-title":"Proc. 1st Annu. Conf. Robot Learn.","volume":"78","author":"Rusu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.06.011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmp.2008.12.005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13673"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.2466\/pms.106.2.461-472"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2007.19.11.1854"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.02.066"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3758\/s13421-021-01168-z"},{"key":"ref31","article-title":"Learning to multi-task by active sampling","author":"Sharma","year":"2017","journal-title":"arXiv:1702.06053"},{"key":"ref32","article-title":"Adaptive scheduling for multi-task learning","author":"Jean","year":"2019","journal-title":"arXiv:1909.06434"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.004"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.12.006.2007"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3276597"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00115"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3062728"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2933900"},{"key":"ref39","article-title":"Exploration by random network distillation","author":"Burda","year":"2018","journal-title":"arXiv:1810.12894"},{"key":"ref40","article-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2018","journal-title":"arXiv:1802.06070"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref42","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","author":"Narvekar","year":"2020","journal-title":"arXiv:2003.04960"},{"key":"ref43","first-page":"5238","article-title":"Curriculum learning by transfer learning: Theory and experiments with deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Weinshall"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2014.6983028"},{"key":"ref45","article-title":"Learning to execute","author":"Zaremba","year":"2014","journal-title":"arXiv:1410.4615"},{"key":"ref46","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref47","article-title":"PathNet: Evolution channels gradient descent in super neural networks","author":"Fernando","year":"2017","journal-title":"arXiv:1701.08734"},{"key":"ref48","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"issue":"274","key":"ref49","first-page":"1","article-title":"CleanRL: High-quality single-file implementations of deep reinforcement learning algorithms","volume":"23","author":"Huang","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","volume-title":"Flow: The Psychology of Optimal Experience","author":"Csikszentmihalyi","year":"1990"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref52","volume-title":"RL Baselines3 Zoo","author":"Raffin","year":"2020"},{"key":"ref53","article-title":"Implementation matters in deep RL: A case study on PPO and TRPO","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Engstrom"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722000625"},{"key":"ref55","article-title":"Gymnasium","author":"Towers","journal-title":"Zenodo"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(03)00169-7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1126\/science.275.5306.1593"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1320116110"},{"key":"ref60","article-title":"Continual backprop: Stochastic gradient descent with persistent randomness","author":"Dohare","year":"2021","journal-title":"arXiv:2108.06325"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(98)01221-2"},{"key":"ref62","first-page":"S598","article-title":"Separated modules for visuomotor control and learning in the cerebellum: A functional MRI study","volume-title":"Proc. 3rd Int. Conf. Funct. Mapping Human Brain","volume":"5","author":"Imamizu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/35003194"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10531261.pdf?arnumber=10531261","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T17:43:09Z","timestamp":1716399789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10531261\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3402089","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}